MTPLX
The fastest way to run Inkling 2 Mini, Qwen 3.8 and Ternary Bonsai 2 27B on a Mac: Inkling 2 Mini at up to 128.8 tok/s and Flash Next at 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
youssofal/MTPLX
View on GitHub ↗The fastest way to run Inkling 2 Mini, Qwen 3.8 and Ternary Bonsai 2 27B on a Mac: Inkling 2 Mini at up to 128.8 tok/s and Flash Next at 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.
MTPLX grew +4.1% in the last 30 days, ranks 75th of 539 in Local Runtime / Inference Engine, actively maintained, last commit today.
Star trajectory
64 days tracked+4.1% in 30d, above the Local Runtime / Inference Engine median of +1.9%.
Last commit today, fresher than the median of 6d.
How it compares in Local Runtime / Inference Engine
Ranked 75th of 539 by stars.
Related repos
Ranked by shared tags, then keywords, then starsWhere MTPLX sits
Hover or focus a node for details. Click to open it.
- This repo
- Related repo
- Tag or category
Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.
+15 (+1.8%) in 30d · Committed 49d ago · Rust · Other license
Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime
Inference engine for Intel devices. Serve LLMs, VLMs, Whisper, Kokoro-TTS, Embedding and Rerank models over…
+10 (+1.8%) in 30d · Committed yesterday · Python · Apache-2.0
Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime
CPU-first LLM inference server on llama.cpp. Runs useful models on free-tier ARM boxes; rewriting the input…
+0 (+0.0%) in 30d · Committed 40d ago · C++ · MIT
Shares Local Runtime / Inference Engine, Web / Edge / On-Device Runtime, Inference Optimization
The local AI app built for the Mac. Run LLMs like Qwen, Gemma and GPT-OSS on Apple Silicon, including models…
+17 (+28%) in 30d · Committed today · Swift · Apache-2.0
Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime
Gemma 4 26B-A4B inference in ~2 GB of RAM on any M-series MacBook
+442 (+6.3%) in 30d · Committed 7d ago · Swift · Apache-2.0
Shares Web / Edge / On-Device Runtime, Inference Optimization, Local Runtime / Inference Engine
Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable
+93 (+8.4%) in 30d · Committed 15d ago · Python · MIT
Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime
A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console…
Committed today · C# · BSD-3-Clause
Shares Local Runtime / Inference Engine, Inference Optimization, Web / Edge / On-Device Runtime
Run a 105 GB AI model on a Mac that can't hold it. Qwen3.8-Flash-Next 4-bit, streamed from SSD on 16–64 GB…
+193 (+40%) in 30d · Committed 4d ago · Swift · MIT
Shares Web / Edge / On-Device Runtime, Inference Optimization, Local Runtime / Inference Engine
Open-source local AI workspace — advancing on-device inference.
-6 (-1.5%) in 30d · Committed 34d ago · TypeScript · Apache-2.0
Shares Local Runtime / Inference Engine, Web / Edge / On-Device Runtime, Inference Optimization
Run large language models locally on Intel Macs with AMD GPUs - native macOS app with Metal acceleration
+48 (+22%) in 30d · Committed 3d ago · Swift · GPL-3.0
Shares Local Runtime / Inference Engine, Web / Edge / On-Device Runtime, Inference Optimization
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 52
- Forks
- 214
- Watchers
- 22
- Open issues
- 37
- Releases
- 58
- Created
- 2026-05-02
- Stars this week
- +27
You've seen where MTPLX stands today.
Get the moves before everyone else: the 5 Local Runtime / Inference Engine repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.